x86/percpu, x86/irq: Relax {set,get}_irq_regs()

Nadav reported that since the this_cpu_*() ops got asm-volatile
constraints on, code generation suffered for do_IRQ(), but since this
is all with IRQs disabled we can use __this_cpu_*().

  smp_x86_platform_ipi                                      234        222   -12,+0
  smp_kvm_posted_intr_ipi                                    74         66   -8,+0
  smp_kvm_posted_intr_wakeup_ipi                             86         78   -8,+0
  smp_apic_timer_interrupt                                  292        284   -8,+0
  smp_kvm_posted_intr_nested_ipi                             74         66   -8,+0
  do_IRQ                                                    195        187   -8,+0
Reported-by: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/irq_regs.h

@@ -16,7 +16,7 @@ DECLARE_PER_CPU(struct pt_regs *, irq_regs);
 
 static inline struct pt_regs *get_irq_regs(void)
 {
-	return this_cpu_read(irq_regs);
+	return __this_cpu_read(irq_regs);
 }
 
 static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
@@ -24,7 +24,7 @@ static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
 	struct pt_regs *old_regs;
 
 	old_regs = get_irq_regs();
-	this_cpu_write(irq_regs, new_regs);
+	__this_cpu_write(irq_regs, new_regs);
 
 	return old_regs;
 }